Disclosed herein are various for a providing streaming content based on clustered behavior patterns. In an embodiment, a request for content is received from a first receiver associated with a first user. Each member is grouped into the cluster based a user interface browsing behavior pattern. A plurality of skip commands associated with the requested content from a plurality of receivers associated with at least a subset of the plurality of users of the cluster is received. A crowd source skip history is generated for the requested content for the cluster using at least the received plurality of skip commands. The requested content is transmit to the first receiver associated with the first user who is a member of the cluster, wherein a portion of the requested content identified by the crowd source skip history is excluded from the transmitted requested content.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method comprising: receiving a request for content from a first receiver associated with a first user; determining that the first user is a member of a cluster of a plurality of users; determining a crowd source skip history for the requested content for the cluster using a plurality of skip commands associated with the requested content from a plurality of receivers associated with at least a subset of the plurality of users of the cluster; determining that the plurality of skip commands are selections of new content from the plurality of receivers at a timestamp of the requested content; determining user-specific new content to provide to the first user based on a viewing profile of the first user; and transmitting the requested content to the first receiver associated with the first user who is a member of the cluster, wherein at the timestamp, the determined user-specific new content is provided to the first user based on the viewing profile of the first user in lieu of a subsequent portion of the requested content after the timestamp.
2. The method of claim 1 , wherein the cluster is based on a user interface browsing behavior pattern that indicates an order in which one or more user interface components are navigated by at least a subset of the plurality of users.
3. The method of claim 1 , wherein the cluster is based on a user interface browsing behavior pattern that indicates one or more user interface components over which at least a subset of the plurality of users hovered.
4. The method of claim 1 , wherein the cluster is based on a user interface browsing behavior pattern that indicates one or more user interface components which at least a subset of the plurality of users visited multiple times.
5. The method of claim 1 , wherein the cluster is based on a user interface browsing behavior pattern that indicates one or more user interface components which at least a subset of the plurality of users clicked.
6. The method of claim 1 , wherein each member is grouped into the cluster based on both a user interface browsing behavior pattern and a viewing pattern.
7. The method of claim 6 , wherein the viewing pattern indicates a portion of a video over which at least a subset of the plurality of users skipped.
8. The method of claim 1 , wherein new content is selected based at least in part on a length of its duration corresponding to a duration of the requested content.
9. A system comprising: a memory; and at least one processor coupled to the memory and configured to perform operations comprising: receiving a request for content from a first receiver associated with a first user; determining that the first user is a member of a cluster of a plurality of users; determining a crowd source skip history for the requested content for the cluster using a plurality of skip commands associated with the requested content from a plurality of receivers associated with at least a subset of the plurality of users of the cluster; determining that the plurality of skip commands are selections of new content from the plurality of receivers at a timestamp of the requested content; determining user-specific new content to provide to the first user based on a viewing profile of the first user; and transmitting the requested content to the first receiver associated with the first user who is a member of the cluster, wherein at the timestamp, the determined user-specific new content is provided to the first user based on the viewing profile of the first user in lieu of a subsequent portion of the requested content after the timestamp.
10. The system of claim 9 , wherein the cluster is based on a user interface browsing behavior pattern that indicates an order in which one or more user interface components are navigated by at least a subset of the plurality of users.
11. The system of claim 9 , wherein the cluster is based on a user interface browsing behavior pattern that indicates one or more user interface components over which at least a subset of the plurality of users hovered.
12. The system of claim 9 , wherein the cluster is based on a user interface browsing behavior pattern that indicates one or more user interface components which at least a subset of the plurality of users visited multiple times.
13. The system of claim 9 , wherein the cluster is based on a user interface browsing behavior pattern that indicates one or more user interface components which at least a subset of the plurality of users clicked.
14. The system of claim 9 , wherein each member is grouped into the cluster based on both a user interface browsing behavior pattern and a viewing pattern.
15. The system of claim 14 , wherein the viewing pattern indicates a portion of a video over which at least a subset of the plurality of users skipped.
16. A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising: receiving a request for content from a first receiver associated with a first user; determining that the first user is a member of a cluster of a plurality of users; determining a crowd source skip history for the requested content for the cluster using a plurality of skip commands associated with the requested content from a plurality of receivers associated with at least a subset of the plurality of users of the cluster; determining that the plurality of skip commands are selections of new content from the plurality of receivers at a timestamp of the requested content; determining user-specific new content to provide to the first user based on a viewing profile of the first user; and transmitting the requested content to the first receiver associated with the first user who is a member of the cluster, wherein at the timestamp, the determined user-specific new content is provided to the first user based on the viewing profile of the first user in lieu of a subsequent portion of the requested content after the timestamp.
17. The non-transitory computer-readable medium of claim 16 , wherein the cluster is based on a user interface browsing behavior pattern that indicates an order in which one or more user interface components are navigated by at least a subset of the plurality of users.
18. The non-transitory computer-readable medium of claim 16 , wherein the cluster is based on a user interface browsing behavior pattern that indicates one or more user interface components over which at least a subset of the plurality of users hovered.
19. The non-transitory computer-readable medium of claim 16 , wherein the cluster is based on a user interface browsing behavior pattern that indicates one or more user interface components which at least a subset of the plurality of users visited multiple times.
20. The non-transitory computer-readable medium of claim 16 , wherein the cluster is based on a user interface browsing behavior pattern that indicates one or more user interface components which at least a subset of the plurality of users clicked.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 30, 2021
July 5, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.